def get_transformation_for_division(train_X_all, raw_features):
unary_transformations: List[UnaryTransformation] = []
binary_transformations: List[Transformation] = []
#unary_transformations.append(PandasDiscretizerTransformation(number_bins=10))
unary_transformations.append(MinMaxScalingTransformation())
unary_transformations.append(MDLPDiscretizerTransformation())
unary_transformations.append(OneDivisionTransformation())
unary_transformations.append(MinusTransformation())
unary_transformations.append(ImputationTransformation('mean'))
#unary_transformations.append(ImputationTransformation('median'))
#unary_transformations.append(ImputationTransformation('most_frequent'))
binary_transformations.extend(
HigherOrderCommutativeClassGenerator(
2,
methods=[np.nansum, np.nanprod],
sympy_methods=[sympy.Add, sympy.Mul]).produce())
binary_transformations.extend(
GroupByThenGenerator(
2,
methods=[np.nanmax, np.nanmin, np.nanmean, np.nanstd],
sympy_methods=[
groupbythenmax, groupbythenmin, groupbythenmean, groupbythenstd
]).produce())
unary_transformations.extend(
OneHotGenerator(train_X_all, raw_features).produce())
return unary_transformations, binary_transformations
def get_transformation_for_cat_feature_space(train_X_all, raw_features):
unary_transformations: List[UnaryTransformation] = []
binary_transformations: List[Transformation] = []
unary_transformations.append(
PandasDiscretizerTransformation(number_bins=10))
unary_transformations.append(MinMaxScalingTransformation())
binary_transformations.extend(
HigherOrderCommutativeClassGenerator(
2,
methods=[np.nansum, np.nanprod],
sympy_methods=[sympy.Add, sympy.Mul]).produce())
binary_transformations.extend(
NumpyBinaryClassGenerator(methods=[np.divide, np.subtract],
sympy_methods=[sympy_divide,
sympy_subtract]).produce())
binary_transformations.extend(
GroupByThenGenerator(
2,
methods=[np.nanmax, np.nanmin, np.nanmean, np.nanstd],
sympy_methods=[
groupbythenmax, groupbythenmin, groupbythenmean, groupbythenstd
]).produce())
unary_transformations.extend(
OneHotGenerator(train_X_all, raw_features).produce())
return unary_transformations, binary_transformations
def produce_features(self):
unary_transformations: List[UnaryTransformation] = []
unary_transformations.append(
PandasDiscretizerTransformation(number_bins=10))
unary_transformations.append(MinMaxScalingTransformation())
higher_order_transformations: List[Transformation] = []
higher_order_transformations.extend(
HigherOrderCommutativeClassGenerator(
2, methods=[np.nansum, np.nanprod]).produce())
higher_order_transformations.extend(
NumpyBinaryClassGenerator(
methods=[np.divide, np.subtract]).produce())
# count is missing
higher_order_transformations.extend(
GroupByThenGenerator(
2, methods=[np.nanmax, np.nanmin, np.nanmean,
np.nanstd]).produce())
Fui = self.generate_features1(unary_transformations, self.raw_features)
Fi_and_Fui = []
Fi_and_Fui.extend(self.raw_features)
Fi_and_Fui.extend(Fui)
Foi = self.generate_features1(higher_order_transformations, Fi_and_Fui)
Foui = self.generate_features1(unary_transformations, Foi)
Fi_cand = []
Fi_cand.extend(Fui)
Fi_cand.extend(Foi)
Fi_cand.extend(Foui)
return Fi_cand
def generate_candidates(self):
unary_transformations: List[UnaryTransformation] = []
unary_transformations.append(
PandasDiscretizerTransformation(number_bins=10))
unary_transformations.append(MinMaxScalingTransformation())
higher_order_transformations: List[Transformation] = []
higher_order_transformations.extend(
HigherOrderCommutativeClassGenerator(
2, methods=[np.nansum, np.nanprod]).produce())
higher_order_transformations.extend(
NumpyBinaryClassGenerator(
methods=[np.divide, np.subtract]).produce())
#count is missing
higher_order_transformations.extend(
GroupByThenGenerator(
2, methods=[np.nanmax, np.nanmin, np.nanmean,
np.nanstd]).produce())
transformations = []
transformations.extend(unary_transformations)
transformations.extend(higher_order_transformations)
#transformations.append(IdentityTransformation(2))
print("unary transformations: " + str(len(unary_transformations)))
print("higherorder transformations: " +
str(len(higher_order_transformations)))
features = self.Fi
'''
graph = nx.DiGraph()
graph.add_node('root')
for f in features:
graph.add_node(str(f))
graph.node[str(f)]['feature'] = f
graph.add_edge('root', str(f))
'''
F0 = features
F = []
F.append(F0)
'''
for depth in range(2):
F_t_plus_1 = []
for t_i in transformations:
for f_i in t_i.get_combinations(list(itertools.chain(*F[0:depth+1]))):
if t_i.is_applicable(f_i):
current_feature = CandidateFeature(copy.deepcopy(t_i), f_i)
print(current_feature)
graph.add_node(str(current_feature))
graph.node[str(current_feature)]['feature'] = current_feature
for parent_feature in f_i:
graph.add_edge(str(parent_feature), str(current_feature))
F_t_plus_1.append(current_feature)
F.append(F_t_plus_1)
print(len(list(itertools.chain(*F))))
#self.plot_graph(graph)
'''
for depth in range(3):
results = self.generate_in_parallel(transformations,
F[0:depth + 1])
F.append(results)
print(len(list(itertools.chain(*F))))